Rabilloud Noémie, Allaume Pierre, Acosta Oscar, De Crevoisier Renaud, Bourgade Raphael, Loussouarn Delphine, Rioux-Leclercq Nathalie, Khene Zine-Eddine, Mathieu Romain, Bensalah Karim, Pecot Thierry, Kammerer-Jacquet Solene-Florence
Impact TEAM, Laboratoire Traitement du Signal et de l'Image (LTSI) INSERM, Rennes University, 35033 Rennes, France.
Department of Pathology, Rennes University Hospital, 2 rue Henri Le Guilloux, CEDEX 09, 35033 Rennes, France.
Diagnostics (Basel). 2023 Aug 14;13(16):2676. doi: 10.3390/diagnostics13162676.
Deep learning (DL), often called artificial intelligence (AI), has been increasingly used in Pathology thanks to the use of scanners to digitize slides which allow us to visualize them on monitors and process them with AI algorithms. Many articles have focused on DL applied to prostate cancer (PCa). This systematic review explains the DL applications and their performances for PCa in digital pathology. Article research was performed using PubMed and Embase to collect relevant articles. A Risk of Bias (RoB) was assessed with an adaptation of the QUADAS-2 tool. Out of the 77 included studies, eight focused on pre-processing tasks such as quality assessment or staining normalization. Most articles ( = 53) focused on diagnosis tasks like cancer detection or Gleason grading. Fifteen articles focused on prediction tasks, such as recurrence prediction or genomic correlations. Best performances were reached for cancer detection with an Area Under the Curve (AUC) up to 0.99 with algorithms already available for routine diagnosis. A few biases outlined by the RoB analysis are often found in these articles, such as the lack of external validation. This review was registered on PROSPERO under CRD42023418661.
深度学习（DL），通常被称为人工智能（AI），由于使用扫描仪将载玻片数字化，使得我们能够在显示器上可视化并使用人工智能算法进行处理，因此在病理学中的应用越来越广泛。许多文章都聚焦于深度学习在前列腺癌（PCa）中的应用。本系统评价阐述了深度学习在数字病理学中对前列腺癌的应用及其性能。通过使用PubMed和Embase进行文献检索以收集相关文章。采用改编后的QUADAS - 2工具评估偏倚风险（RoB）。在纳入的77项研究中，有8项聚焦于预处理任务，如质量评估或染色标准化。大多数文章（n = 53）聚焦于诊断任务，如癌症检测或Gleason分级。15篇文章聚焦于预测任务，如复发预测或基因组相关性。对于癌症检测，使用已可用于常规诊断的算法，曲线下面积（AUC）高达0.99时可达到最佳性能。在这些文章中经常发现RoB分析所概述的一些偏倚，如缺乏外部验证。本综述已在PROSPERO上注册，注册号为CRD42023418661。
